> For the complete documentation index, see [llms.txt](https://docs.getdot.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.getdot.ai/integrations/semantic-layers/steep.md).
# Steep
Connect Dot to Steep to query your metrics using natural language
Connect Dot to your [Steep](https://steep.app) semantic layer to query metrics, dimensions, and slices using natural language. Dot syncs your metric definitions, dimensions, and their descriptions so you can ask questions about your data without writing code.
{% hint style="info" %}
**Requirements**
* A **Steep account** with at least one metric defined
* A **Steep API key** — generate one in Steep under **Settings → API**
{% endhint %}
## Connect to Steep
1. Go to **Settings → Semantic Layers → Steep**
2. Enter your **API Key**
3. Click **Connect**
4. Dot will sync your metrics and dimensions
{% hint style="success" %}
**Generating an API key**
In Steep, go to **Settings → API** and create a new API key. Copy the key and paste it into Dot.
{% endhint %}
## What Gets Synced
When you connect Steep, Dot imports:
* **Metrics** — each metric appears as a table (e.g., revenue, order\_volume)
* **Dimensions** — appear as columns on each metric, with their data types
* **Descriptions** — metric and dimension descriptions are synced for context
* **Slices** — predefined filters listed in metric descriptions (e.g., "UK", "Enterprise")
* **Related metrics** — noted in descriptions so Dot can suggest complementary data
Dot periodically re-syncs to pick up new or changed metrics. You can also trigger a manual sync from the connection settings.
## How Queries Work
When you ask a question, Dot generates a `steep_query()` call that fetches data for one metric at a time. Queries support:
* **Breakdowns** — group results by up to 2 dimensions (e.g., by Country, by Product Category)
* **Filters** — narrow results to specific dimension values
* **Slices** — use predefined filters for common segments
* **Time ranges** — specify date ranges and time granularity (daily, weekly, monthly, quarterly, yearly)
---
# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.
## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation by asking a question.
Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:
```
GET https://docs.getdot.ai/integrations/semantic-layers/steep.md?ask=&goal=
```
`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.
Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.
